Program Structure for Fourth Year Information Technology

Semester VII & VIII

UNIVERSITY OFMUMBAI
(With Effect from2022-2023)
Semester VII
Teaching Scheme
Credits Assigned
Course (Contact Hours)
Course Name
Code Pract.
Theory Theory Pract. Total
Tut.
ITC701 AI and DS –II 3 -- 3 -- 3
ITC702 Internet of Everything 3 -- 3 3
Department Optional
ITDO701 3 -- 3 -- 3
Course – 3
X
Department
ITDO702 3 -- 3 -- 3
Optional Course –4
X
Institute Optional
ITIO701X 3 -- 3 -- 3
Course – 1
ITL701 Data Science Lab -- 2 -- 1 1
ITL702 IOE Lab -- 2 -- 1 1
ITL703 Secure Application -- 2 -- 1 1
Development
ITL704 Recent Open Source -- 2 -- 1 1
Project Lab
ITP701 Major Project I -- 6# -- 3 3
Total 15 14 15 7 22
Examination Scheme
Term Prac/o
Theory Total
Work ral
Course End Exam.
Course Name Internal Assessment Sem Duration
Code
Exam (in Hrs)

Test1 Test2 Avg

ITC701 AI and DS –II 20 20 20 80 3 -- -- 100

ITC702 Internet of Everything 20 20 20 80 3 -- -- 100
Department
ITDO701 20 20 20 80 3 -- -- 100
Optional Course –3
X
Department
ITDO702 20 20 20 80 3 -- -- 100
Optional Course –4
X
Institute Optional
ILO701X 20 20 20 80 3 -- -- 100
Course – 1
ITL701 Data Science Lab -- -- -- -- -- 25 25 50
ITL702 IOE Lab -- -- -- -- -- 25 25 50
ITL703 Secure Application -- -- -- -- -- 25 25 50
Development
ITL704 Recent Open Source -- -- -- -- -- 25 25 50
Project Lab
ITP701 Major Project I -- -- -- -- -- 25 25 50
Total -- -- 100 400 -- 125 125 750
 Course Code Course Name Theory Practical Tutorial Theory Practical/ Tutorial Total
Oral
03 -- -- 03 -- -- 03
ITC701 AI and DS –II

Course Course
Examination Scheme
Code Name
Theory Marks
Internal assessment End Term
Practical Oral Total
Avg. of 2 Sem. Work
Test1 Test 2
Tests Exam
AI and DS –
ITC701 20 20 20 80 -- -- -- 100
II

Course Objectives:

Sr. No. Course Objectives

The course aims:
1 To model a decision making for a new problem in an uncertain domain.
2 To demonstrate Cognitive skills of Artificial Intelligence.
3 To become familiar with the basics of Fuzzy Logic and Fuzzy Systems.
4 To become familiar with Deep Learning Concepts and Architectures.
5 To define and apply metrics to measure the performance of various learning algorithms.
6 To enable students to analyze data science methods for real world problems.

Course Outcomes:

Sr. No. Course Outcomes Cognitive levels of

attainment as per
Bloom’s Taxonomy
On successful completion, of course, learner/student will be able to:
1 Design models for reasoning with uncertainty as well as the use of unreliable L1,L2,L3
information.
2 Analyze the process of building a Cognitive application. L1,L2,L3,L4
3 Design fuzzy controller system. L1,L2,L3
4 Apply learning concepts to develop real life applications. L1,L2,L3
5 Evaluate performance of learning algorithms. L1,L2,L3,L4,L5
6 Analyze current trends in Data Science. L1,L2,L3,L4

Prerequisite: AI and DS - 1 (ITC604) , Data Mining & Business Intelligence (ITC601)

DETAILED SYLLABUS:

Sr. Module Detailed Content Hours CO

No. Mapping
 02 --
0 Prerequisite Intelligent Agents, Search Techniques, Knowledge and
Reasoning, Data Science, Machine Learning.
04 CO1
Uncertainty in AI, Inference using full joint distributions,
Bayes Theorem, the semantics of Bayesian Networks,
I Uncertainty Inference in Bayesian networks, Decision Theory, Markov
Decision Processes.
Self-learning Topics: Hidden Markov Model (HMM),
Gaussian Mixture Model (GMM).
06 CO2
Foundation of Cognitive Computing, Design Principles for
Cognitive Systems, Natural Language Processing in Support of
a Cognitive System, Representing Knowledge in Taxonomies
Cognitive and Ontologies, Applying Advanced Analytics to Cognitive
II
Computing Computing, The Process of Building a Cognitive Application.

Self-learning Topics: Cognitive Systems such as IBM’s

Watson.

07 CO3
Introduction to Fuzzy Sets, Properties of Fuzzy Sets,
Operations on Fuzzy Sets, Fuzzy Membership Functions,
Fuzzy Relations with Operations and its Properties, Fuzzy
Composition: Max-Min Composition, Max-Product
Fuzzy Logic
Composition, Defuzzification Methods, Architecture of
III & Its
Mamdani Type Fuzzy Control System, Design of Fuzzy
Applications
Controllers like Domestic Shower Controller, Washing
Machine Controller, Water Purifier Controller, etc.

Self-learning Topics: Other Fuzzy Composition

Operations, Fuzzy Inference System (FIS) & ANFIS.
08 CO4
Introduction to Deep Learning, ANN, Machine Learning Vs
Deep Learning, Working of Deep Learning; Convolutional
Neural Network: Introduction, Components of CNN
Architecture, Properties of CNN, Architectures of CNN,
Introduction to Applications of CNN, Recurrent Neural Network: Introduction,
IV
Deep Learning Simple RNN, LSTM Implementation, Deep RNN,
Autoencoder: Introduction, Features, Types, Applications of
Deep Learning.

Self-learning Topics: Restricted Boltzmann Machine

(RBM).
06 CO4
Ensemble Classifiers: Introduction to Ensemble Methods, CO5
Bagging, Boosting, Random forests, Improving classification
accuracy of Class-Imbalanced Data.
Advanced ML
V Classification Metrics for Evaluating Classifier Performance, Holdout
Techniques Method and Random Subsampling, Cross-Validation,
Bootstrap, Model Selection Using Statistical Tests of
Significance, Comparing Classifiers Based on Cost–Benefit
and ROC Curves.
Self-learning Topics: Introduction to ML (Revision),
 Introduction to Reinforcement Learning.

06 CO6
Data Science: applications and case studies, Data science for
Trends and text, image, video, audio. Data science for Multimodal
VI applications in applications.
Data Science
Self-learning Topics: ImageNet Large Scale Visual
Recognition Challenge (ILSVRC).

Text Books:
1. Stuart Russell and Peter Norvig, “Artificial Intelligence: A Modern Approach”, Third Edition, Pearson Education.
2. Judith S. Hurwitz, Marcia Kaufman, Adrian Bowles, “Cognitive Computing and Big Data Analytics”, Wiley India, 2015.
3. S.N. Sivanandam, S.N. Deepa, “Principles of Soft Computing”, Wiley Publication.
4. Dr. S Lovelyn Rose, Dr. L Ashok Kumar, Dr. D Karthika Renuka, “Deep Learning Using Python”, Wiley India, 2020.
5. B. Uma Maheshwari, R. Sujatha, “Introduction to Data Science Practical Approach with R and Python”, Wiley India,
2021.
6. François Chollet, “Deep Learning with Python”, Manning Publications, 2018.
7. Han J, Kamber M, Pei J, “Data Mining Concepts and Techniques”, Third Edition, Morgan Kaufmann.

References:
1. Deepak Khemani, “A First Course in Artificial Intelligence”, McGraw Hill Publication.
2. Ethem Alpaydin , “Introduction to Machine Learning”, PHI Learning Pvt. Ltd.
3. Jon Krohn, Grant Beyleveld, Aglae Bassens, “Deep Learning Illustrated: A Visual, Interactive Guide to Artificial
Intelligence”, Pearson Education.
4. Prateek Joshi, “Artificial Intelligence with Python”, Packt Publishing.

Online References:
Sr. No. Website Links

1 https://d2l.ai/index.html

2 https://onlinecourses.nptel.ac.in/noc20_cs62/preview

3 https://onlinecourses.nptel.ac.in/noc22_cs35/preview

4 https://www.coursera.org/specializations/deep-learning

5 https://onlinecourses.nptel.ac.in/noc22_cs56/preview

Assessment:
Internal Assessment for 20 marks:
Consisting of Two Compulsory Class Tests
Approximately 40% to 50% of syllabus content must be covered in First test and remaining 40% to 50% of syllabus contents
must be covered in second test.

End Semester Examination: Some guidelines for setting the question papers are as:
 Weightage of each module in end semester examination is expected to be/will be proportional to number of respective
lecture hours mentioned in the syllabus.
 Question paper will comprise of total six questions, each carrying 20 marks.
 Q.1 will be compulsory and should cover maximum contents of the syllabus.
 Remaining question will be mixed in nature (for example if Q.2 has part (a) from module 3 then part (b) will be from
any other module. (Randomly selected from all the modules.)